Good Papers: read the good ones

gfnx: Fast and Scalable Library for Generative Flow Networks in JAX

gfnx is a JAX library for training and evaluating GFlowNets that achieves up to 80x speedups over PyTorch benchmarks across diverse tasks.

– ReadersNo votes yet

9/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 9 of 20 reviewers recommend it

lenient 3/5

medium 4/10

strict 2/5

83%Must read

?Must readVote to see the score

NeurIPS 2026APPLIED-AI Higher School of Economics, High AppliedAI Institute independent scientist Skoltech LLM pretraining & scaling laws

Bug or Feature$^2$: Weight Drift, Activation Sparsity, and Spikes

Standard losses and biased activations induce negative weight drift that drives early training dynamics and extreme sparsity across architectures, with squared activations sharply improving accuracy until a cliff near 70% sparsity unless clipping controls intermediate spikes.

Egor Shvetsov, Aleksandr Serkov, Shokorov Viacheslav, Redko Dmitry and 2 more

Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026 · ▲ 1 on Hugging Face · Code ★ 1

– ReadersNo votes yet

13/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 13 of 20 reviewers recommend it

lenient 4/5

medium 7/10

strict 2/5